Paper
6 May 2019 Learning EP-net for identification and segmentation of scanning electron microscopic image
Author Affiliations +
Proceedings Volume 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018); 110693D (2019) https://doi.org/10.1117/12.2524358
Event: Tenth International Conference on Graphic and Image Processing (ICGIP 2018), 2018, Chengdu, China
Abstract
The vertical structure (VS) in nanosheet is important to electrical application because the VS in nanosheet determines the efficiency of solar cells, electrochemical biosensors and etc. The scanning electron microscopy (SEM) provides a way to observe the nanosheet structure; however, the identification of the structure is inaccuracy and when just from human justification. Deep learning gives an efficient method to identification and segmentation in an SEM image, which will enhance the precision. And the identification of VS is beneficial to get the relationship between the VS and electrical application from statistical viewpoint. In this paper we design a deep learning framework to detect the VS in the ZnO nanosheet, which overcomes two issues in the SEM: (i) the intensity inhomogeneity issue; (ii) the interference issue which is caused by other nano structures. And the experimental results exhibit height performance.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Shuo Wang and Zhongyu Hou "Learning EP-net for identification and segmentation of scanning electron microscopic image", Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 110693D (6 May 2019); https://doi.org/10.1117/12.2524358
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Scanning electron microscopy

Convolution

Zinc oxide

Nanowires

Network architectures

Solar cells

RELATED CONTENT


Back to Top